[DEBUG] Loaded weights for easy from safetensors bundle. [START] task=easy env=bess-rl model=meta-llama/Llama-3.1-8B-Instruct [STEP] step=1 action=[-0.9971, 0.8765, -0.9908] reward=0.00 done=false error=null [STEP] step=2 action=[-0.9545, 0.7885, -0.9987] reward=13.05 done=false error=null [STEP] step=3 action=[0.0246, 0.1109, 0.5405] reward=101.14 done=false error=null [STEP] step=4 action=[-0.9919, -0.9993, -0.9974] reward=92.01 done=false error=null [STEP] step=5 action=[0.9879, 0.9882, 0.468] reward=275.49 done=false error=null [STEP] step=6 action=[-0.9851, -0.9981, -0.9126] reward=47.55 done=false error=null [STEP] step=7 action=[-0.984, -0.9988, -0.0065] reward=-0.00 done=false error=null [STEP] step=8 action=[0.5035, -0.0593, 0.1427] reward=77.30 done=false error=null [STEP] step=9 action=[0.6559, -0.9578, -0.9975] reward=92.77 done=false error=null [STEP] step=10 action=[-0.9917, -0.9995, 0.008] reward=0.00 done=false error=null [STEP] step=11 action=[-0.9944, -0.9971, -0.6404] reward=0.00 done=false error=null [STEP] step=12 action=[-0.189, 0.9736, 0.1211] reward=99.13 done=false error=null [STEP] step=13 action=[0.2766, 0.9667, 0.7269] reward=99.62 done=false error=null [STEP] step=14 action=[-0.974, 0.9864, -0.9114] reward=108.50 done=false error=null [STEP] step=15 action=[0.9942, 0.9958, 0.9989] reward=292.70 done=false error=null [STEP] step=16 action=[0.9962, 0.7981, -0.9076] reward=-6.06 done=false error=null [STEP] step=17 action=[-0.977, -0.9706, 0.9149] reward=629.52 done=false error=null [STEP] step=18 action=[-0.9722, -0.6531, -0.8822] reward=1193.85 done=false error=null [STEP] step=19 action=[-0.9989, 0.3722, 0.4911] reward=53.31 done=false error=null [STEP] step=20 action=[-0.887, -0.3098, -0.9928] reward=114.72 done=false error=null [STEP] step=21 action=[0.1369, 0.6709, -0.9954] reward=0.00 done=false error=null [STEP] step=22 action=[-0.9298, 0.9964, 0.9973] reward=334.05 done=false error=null [STEP] step=23 action=[-0.995, 0.9974, 0.9976] reward=348.65 done=false error=null [STEP] step=24 action=[-0.8572, -0.951, -0.6748] reward=-99.72 done=false error=null [STEP] step=25 action=[-0.9984, -0.9832, -0.9996] reward=74.75 done=false error=null [STEP] step=26 action=[-0.9986, -0.989, -0.9988] reward=-0.00 done=false error=null [STEP] step=27 action=[0.9907, 0.9862, -0.984] reward=328.38 done=false error=null [STEP] step=28 action=[0.9925, 0.991, -0.7629] reward=337.09 done=false error=null [STEP] step=29 action=[-0.9783, -0.9637, 0.0596] reward=-20.43 done=false error=null [STEP] step=30 action=[0.9965, 0.9953, 0.9254] reward=429.48 done=false error=null [STEP] step=31 action=[0.9977, 0.9973, 0.9951] reward=288.70 done=false error=null [STEP] step=32 action=[-0.381, -0.9934, -0.1433] reward=-42.66 done=false error=null [STEP] step=33 action=[0.9954, 0.9986, 0.9561] reward=306.05 done=false error=null [STEP] step=34 action=[-0.9985, 0.8009, -0.9921] reward=-8.95 done=false error=null [STEP] step=35 action=[-0.605, 0.7654, -0.9806] reward=-127.04 done=false error=null [STEP] step=36 action=[0.9783, 0.9881, 0.2822] reward=360.68 done=false error=null [STEP] step=37 action=[-0.9185, -0.9963, 0.8953] reward=43.54 done=false error=null [STEP] step=38 action=[-0.315, 0.9941, 0.2278] reward=51.86 done=false error=null [STEP] step=39 action=[0.8201, 0.9602, 0.7773] reward=48.67 done=false error=null [STEP] step=40 action=[-0.9821, 0.9971, 0.9744] reward=140.70 done=false error=null [STEP] step=41 action=[-0.2822, 0.7705, 0.9325] reward=0.00 done=false error=null [STEP] step=42 action=[-0.9843, -0.9671, 0.1774] reward=719.58 done=false error=null [STEP] step=43 action=[-0.9693, -0.9706, 0.8856] reward=914.28 done=false error=null [STEP] step=44 action=[-0.973, -0.9965, 0.0292] reward=310.91 done=false error=null [STEP] step=45 action=[-0.896, -0.9924, -0.9704] reward=0.00 done=false error=null [STEP] step=46 action=[-0.9603, 0.9933, 0.9934] reward=211.63 done=false error=null [STEP] step=47 action=[-0.9645, 0.9941, 0.9987] reward=388.21 done=false error=null [STEP] step=48 action=[-0.9846, 0.9372, 0.9391] reward=207.24 done=false error=null [STEP] step=49 action=[0.9876, 0.9961, -0.9957] reward=-0.00 done=false error=null [STEP] step=50 action=[0.9911, 0.9968, -0.6829] reward=-0.00 done=false error=null [STEP] step=51 action=[-0.8274, -0.5466, -0.9822] reward=-168.45 done=false error=null [STEP] step=52 action=[-0.9913, -0.9351, -0.9888] reward=85.23 done=false error=null [STEP] step=53 action=[0.9907, 0.9855, 0.9486] reward=367.80 done=false error=null [STEP] step=54 action=[0.9849, 0.9894, 0.719] reward=441.89 done=false error=null [STEP] step=55 action=[-0.4456, -0.68, 0.9172] reward=-26.85 done=false error=null [STEP] step=56 action=[-0.9998, -0.9733, -0.9968] reward=253.25 done=false error=null [STEP] step=57 action=[0.9986, 0.9973, 0.7736] reward=361.89 done=false error=null [STEP] step=58 action=[-0.9966, 0.9937, 0.9021] reward=171.29 done=false error=null [STEP] step=59 action=[-0.9896, -0.9202, -0.7939] reward=8.82 done=false error=null [STEP] step=60 action=[-0.874, 0.9817, -0.3423] reward=-31.97 done=false error=null [STEP] step=61 action=[0.9886, 0.9988, 0.9932] reward=339.49 done=false error=null [STEP] step=62 action=[-0.9745, 0.4516, 0.2333] reward=-0.96 done=false error=null [STEP] step=63 action=[-0.4436, -0.6541, 0.9991] reward=4.39 done=false error=null [STEP] step=64 action=[-0.1948, 0.9972, 0.9972] reward=368.40 done=false error=null [STEP] step=65 action=[-0.9917, 0.9869, 0.2161] reward=0.00 done=false error=null [STEP] step=66 action=[-0.9766, -0.9935, -0.9698] reward=803.09 done=false error=null [STEP] step=67 action=[0.8035, 0.9959, 0.9531] reward=-378.81 done=false error=null [STEP] step=68 action=[0.9956, -0.9708, 0.9969] reward=-22.61 done=false error=null [STEP] step=69 action=[-0.9802, -0.9997, -0.9817] reward=888.85 done=false error=null [STEP] step=70 action=[-0.9922, 0.6763, 0.9708] reward=22.83 done=false error=null [STEP] step=71 action=[-0.5025, -0.9961, 0.9961] reward=71.87 done=false error=null [STEP] step=72 action=[-0.9881, -0.9158, 0.5981] reward=-233.04 done=false error=null [STEP] step=73 action=[0.81, 0.9926, 0.923] reward=328.23 done=false error=null [STEP] step=74 action=[-0.5226, -0.78, -0.9984] reward=78.41 done=false error=null [STEP] step=75 action=[-0.9939, -0.9844, -0.9942] reward=40.00 done=false error=null [STEP] step=76 action=[0.9948, 0.9975, -0.9883] reward=322.23 done=false error=null [STEP] step=77 action=[-0.9681, -0.7313, -0.9922] reward=-54.20 done=false error=null [STEP] step=78 action=[0.9914, 0.9964, 0.9088] reward=322.03 done=false error=null [STEP] step=79 action=[-0.4546, 0.5427, 0.9958] reward=145.99 done=false error=null [STEP] step=80 action=[-0.5498, -0.86, -0.9985] reward=99.08 done=false error=null [STEP] step=81 action=[0.424, -0.9455, 0.9051] reward=9.79 done=false error=null [STEP] step=82 action=[-0.9257, 0.9963, 0.9991] reward=306.71 done=false error=null [STEP] step=83 action=[-0.984, 0.9945, 0.9936] reward=91.61 done=false error=null [STEP] step=84 action=[0.9971, 0.9975, 0.9973] reward=-0.00 done=false error=null [STEP] step=85 action=[-0.9968, -0.0051, -0.9903] reward=59.94 done=false error=null [STEP] step=86 action=[-0.978, -0.0693, 0.6854] reward=-4.35 done=false error=null [STEP] step=87 action=[-0.6888, 0.9956, 0.9874] reward=329.28 done=false error=null [STEP] step=88 action=[-0.7518, 0.9742, 0.9873] reward=122.88 done=false error=null [STEP] step=89 action=[-0.9768, -0.4176, 0.7431] reward=507.87 done=false error=null [STEP] step=90 action=[-0.9678, 0.8203, 0.1611] reward=-7.85 done=false error=null [STEP] step=91 action=[-0.9697, 0.9955, 0.915] reward=-388.99 done=false error=null [STEP] step=92 action=[-0.9928, -0.9963, -0.9652] reward=620.25 done=false error=null [STEP] step=93 action=[-0.9915, -0.9982, -0.9951] reward=591.32 done=false error=null [STEP] step=94 action=[-0.9971, -0.9928, -0.9198] reward=-16.41 done=false error=null [STEP] step=95 action=[-0.9986, -0.9938, -0.9317] reward=-0.00 done=false error=null [STEP] step=96 action=[-0.9973, 0.9953, 0.85] reward=287.97 done=false error=null [STEP] step=97 action=[-0.9984, -0.6758, -0.9994] reward=52.41 done=false error=null [STEP] step=98 action=[-0.9931, -0.9184, -0.9909] reward=0.00 done=false error=null [STEP] step=99 action=[0.9895, 0.9935, 0.9564] reward=479.93 done=false error=null [STEP] step=100 action=[-0.9201, -0.8861, -0.9829] reward=-127.41 done=false error=null [STEP] step=101 action=[0.2689, -0.9056, -0.9959] reward=-0.00 done=false error=null [STEP] step=102 action=[0.2476, -0.3632, -0.9859] reward=-0.00 done=false error=null [STEP] step=103 action=[0.9815, 0.9796, -0.9535] reward=235.41 done=false error=null [STEP] step=104 action=[0.6013, -0.997, -0.9602] reward=63.46 done=false error=null [STEP] step=105 action=[-0.5431, -0.9907, 0.4979] reward=-0.00 done=false error=null [STEP] step=106 action=[-0.9799, 0.9877, -0.9932] reward=-0.00 done=false error=null [STEP] step=107 action=[0.9894, 0.9875, 0.9941] reward=563.31 done=false error=null [STEP] step=108 action=[0.6332, 0.9869, -0.5552] reward=163.77 done=false error=null [STEP] step=109 action=[-0.379, 0.9502, 0.885] reward=64.12 done=false error=null [STEP] step=110 action=[-0.9816, 0.9947, 0.2907] reward=-0.00 done=false error=null [STEP] step=111 action=[0.9254, 0.9953, 0.8653] reward=-0.00 done=false error=null [STEP] step=112 action=[0.9889, -0.9888, 0.6309] reward=-0.00 done=false error=null [STEP] step=113 action=[-0.989, 0.9354, 0.473] reward=0.00 done=false error=null [STEP] step=114 action=[-0.9948, 0.985, -0.9697] reward=581.26 done=false error=null [STEP] step=115 action=[-0.9933, -0.9996, 0.9813] reward=597.75 done=false error=null [STEP] step=116 action=[-0.9172, -0.993, -0.6036] reward=390.89 done=false error=null [STEP] step=117 action=[-0.9935, -0.9986, -0.9986] reward=0.00 done=false error=null [STEP] step=118 action=[0.6912, -0.9961, -0.8402] reward=-0.00 done=false error=null [STEP] step=119 action=[0.5863, -0.9852, -0.8008] reward=0.00 done=false error=null [STEP] step=120 action=[-0.7818, 0.9983, 0.1739] reward=35.25 done=false error=null [STEP] step=121 action=[0.9811, 0.8984, -0.9886] reward=275.49 done=false error=null [STEP] step=122 action=[-0.9957, -0.9002, -0.9927] reward=145.76 done=false error=null [STEP] step=123 action=[-0.9975, -0.6267, -0.9986] reward=-19.06 done=false error=null [STEP] step=124 action=[0.9821, 0.998, -0.2208] reward=338.21 done=false error=null [STEP] step=125 action=[-0.9908, -0.963, -0.9594] reward=60.46 done=false error=null [STEP] step=126 action=[0.7161, -0.7491, -0.286] reward=-0.00 done=false error=null [STEP] step=127 action=[0.9994, 0.9909, 0.9927] reward=438.31 done=false error=null [STEP] step=128 action=[0.9952, 0.9736, -0.8722] reward=209.90 done=false error=null [STEP] step=129 action=[0.9972, 0.9954, 0.403] reward=263.70 done=false error=null [STEP] step=130 action=[-0.9995, 0.9972, -0.905] reward=-57.28 done=false error=null [STEP] step=131 action=[-0.983, -0.9611, -0.4788] reward=130.02 done=false error=null [STEP] step=132 action=[-0.9888, 0.9994, -0.8523] reward=8.19 done=false error=null [STEP] step=133 action=[-0.9866, 0.3147, 0.3533] reward=-0.00 done=false error=null [STEP] step=134 action=[0.8805, 0.9984, -0.0443] reward=299.10 done=false error=null [STEP] step=135 action=[-0.9865, 0.9878, 0.978] reward=415.57 done=false error=null [STEP] step=136 action=[-0.979, 0.9908, 0.996] reward=313.15 done=false error=null [STEP] step=137 action=[-0.9968, -0.9834, -0.1145] reward=649.03 done=false error=null [STEP] step=138 action=[-0.9959, 0.9611, -0.91] reward=503.13 done=false error=null [STEP] step=139 action=[-0.9943, -0.685, 0.4546] reward=234.85 done=false error=null [STEP] step=140 action=[-0.9913, -0.9911, -0.982] reward=0.00 done=false error=null [STEP] step=141 action=[-0.466, 0.974, -0.9886] reward=0.00 done=false error=null [STEP] step=142 action=[0.5413, -0.9014, 0.9611] reward=-95.51 done=false error=null [STEP] step=143 action=[-0.8791, -0.9295, 0.5576] reward=44.03 done=false error=null [STEP] step=144 action=[-0.9929, -0.0492, 0.9896] reward=-0.00 done=false error=null [STEP] step=145 action=[0.378, -0.9924, -0.9961] reward=-0.00 done=false error=null [STEP] step=146 action=[-0.8913, -0.5147, -0.9888] reward=-0.00 done=false error=null [STEP] step=147 action=[-0.4615, 0.7648, -0.9882] reward=-0.00 done=false error=null [STEP] step=148 action=[0.6087, 0.9393, 0.4338] reward=236.04 done=false error=null [STEP] step=149 action=[0.9711, 0.9722, 0.1711] reward=257.15 done=false error=null [STEP] step=150 action=[0.1289, -0.9527, -0.9985] reward=116.61 done=false error=null [STEP] step=151 action=[-0.9107, -0.9943, -0.9997] reward=160.39 done=false error=null [STEP] step=152 action=[0.9987, 0.9915, 0.8982] reward=395.79 done=false error=null [STEP] step=153 action=[0.9506, -0.9546, 0.9412] reward=103.34 done=false error=null [STEP] step=154 action=[-0.9822, -0.9935, -0.957] reward=-38.97 done=false error=null [STEP] step=155 action=[-0.9923, 0.9581, 0.2479] reward=26.30 done=false error=null [STEP] step=156 action=[-0.9906, -0.691, -0.0775] reward=6.52 done=false error=null [STEP] step=157 action=[-0.2512, -0.968, -0.2452] reward=0.00 done=false error=null [STEP] step=158 action=[-0.9889, 0.9953, 0.995] reward=500.17 done=false error=null [STEP] step=159 action=[0.9746, 0.9951, 0.9761] reward=222.03 done=false error=null [STEP] step=160 action=[-0.9837, -0.2452, 0.9988] reward=-7.94 done=false error=null [STEP] step=161 action=[-0.9956, 0.9973, -0.2898] reward=134.28 done=false error=null [STEP] step=162 action=[-0.7356, -0.1636, -0.816] reward=1064.42 done=false error=null [STEP] step=163 action=[-0.8064, 0.9947, 0.9997] reward=-68.80 done=false error=null [STEP] step=164 action=[-0.9854, -0.9957, -0.965] reward=730.73 done=false error=null [STEP] step=165 action=[0.7936, -0.9964, -0.9757] reward=36.29 done=false error=null [STEP] step=166 action=[0.6296, -0.9828, 0.4584] reward=13.35 done=false error=null [STEP] step=167 action=[-0.9962, 0.9977, 0.9941] reward=319.81 done=false error=null [STEP] step=168 action=[-0.9334, 0.3014, -0.8902] reward=-103.33 done=false error=null [END] success=true steps=168 score=0.325 rewards=0.00,13.05,101.14,92.01,275.49,47.55,-0.00,77.30,92.77,0.00,0.00,99.13,99.62,108.50,292.70,-6.06,629.52,1193.85,53.31,114.72,0.00,334.05,348.65,-99.72,74.75,-0.00,328.38,337.09,-20.43,429.48,288.70,-42.66,306.05,-8.95,-127.04,360.68,43.54,51.86,48.67,140.70,0.00,719.58,914.28,310.91,0.00,211.63,388.21,207.24,-0.00,-0.00,-168.45,85.23,367.80,441.89,-26.85,253.25,361.89,171.29,8.82,-31.97,339.49,-0.96,4.39,368.40,0.00,803.09,-378.81,-22.61,888.85,22.83,71.87,-233.04,328.23,78.41,40.00,322.23,-54.20,322.03,145.99,99.08,9.79,306.71,91.61,-0.00,59.94,-4.35,329.28,122.88,507.87,-7.85,-388.99,620.25,591.32,-16.41,-0.00,287.97,52.41,0.00,479.93,-127.41,-0.00,-0.00,235.41,63.46,-0.00,-0.00,563.31,163.77,64.12,-0.00,-0.00,-0.00,0.00,581.26,597.75,390.89,0.00,-0.00,0.00,35.25,275.49,145.76,-19.06,338.21,60.46,-0.00,438.31,209.90,263.70,-57.28,130.02,8.19,-0.00,299.10,415.57,313.15,649.03,503.13,234.85,0.00,0.00,-95.51,44.03,-0.00,-0.00,-0.00,-0.00,236.04,257.15,116.61,160.39,395.79,103.34,-38.97,26.30,6.52,0.00,500.17,222.03,-7.94,134.28,1064.42,-68.80,730.73,36.29,13.35,319.81,-103.33 [DEBUG] Loaded weights for medium from safetensors bundle. [START] task=medium env=bess-rl model=meta-llama/Llama-3.1-8B-Instruct [STEP] step=1 action=[-0.9712, 0.0928, -0.9661] reward=0.00 done=false error=null [STEP] step=2 action=[-0.9042, 0.7313, 0.1279] reward=82.05 done=false error=null [STEP] step=3 action=[-0.5858, 0.4686, 0.0454] reward=-10.73 done=false error=null [STEP] step=4 action=[-0.8808, -0.4709, 0.268] reward=10.68 done=false error=null [STEP] step=5 action=[0.9425, 0.9792, 0.3961] reward=275.49 done=false error=null [STEP] step=6 action=[-0.9058, -0.7858, -0.7092] reward=47.55 done=false error=null [STEP] step=7 action=[-0.9569, -0.2679, -0.3635] reward=0.00 done=false error=null [STEP] step=8 action=[0.3501, 0.414, 0.8394] reward=131.74 done=false error=null [STEP] step=9 action=[-0.8927, -0.9063, -0.7363] reward=158.09 done=false error=null [STEP] step=10 action=[-0.9524, -0.5418, -0.9734] reward=0.00 done=false error=null [STEP] step=11 action=[-0.7533, -0.4441, -0.8469] reward=0.00 done=false error=null [STEP] step=12 action=[0.4223, 0.741, 0.6973] reward=109.45 done=false error=null [STEP] step=13 action=[0.9168, 0.9716, 0.5601] reward=99.62 done=false error=null [STEP] step=14 action=[0.9339, 0.9715, -0.978] reward=-76.22 done=false error=null [STEP] step=15 action=[0.9788, 0.9688, 0.9621] reward=0.00 done=false error=null [STEP] step=16 action=[0.9635, 0.9782, 0.8783] reward=0.00 done=false error=null [STEP] step=17 action=[-0.3418, -0.0922, -0.9627] reward=629.52 done=false error=null [STEP] step=18 action=[-0.7319, -0.6816, -0.9911] reward=1193.85 done=false error=null [STEP] step=19 action=[0.9297, 0.8598, -0.9169] reward=-342.85 done=false error=null [STEP] step=20 action=[-0.9481, 0.814, -0.9543] reward=479.34 done=false error=null [STEP] step=21 action=[-0.9806, -0.4075, -0.9247] reward=75.39 done=false error=null [STEP] step=22 action=[0.941, 0.3051, 0.9666] reward=334.05 done=false error=null [STEP] step=23 action=[0.9482, -0.3007, 0.9705] reward=348.65 done=false error=null [STEP] step=24 action=[-0.9584, -0.8515, -0.8661] reward=-99.72 done=false error=null [STEP] step=25 action=[-0.9411, 0.8577, 0.5781] reward=30.49 done=false error=null [STEP] step=26 action=[-0.9351, -0.9037, -0.9767] reward=-57.14 done=false error=null [STEP] step=27 action=[0.9144, 0.9817, -0.1404] reward=407.38 done=false error=null [STEP] step=28 action=[0.7448, 0.9561, 0.2111] reward=337.09 done=false error=null [STEP] step=29 action=[-0.9104, -0.4278, -0.8787] reward=-20.43 done=false error=null [STEP] step=30 action=[0.9607, 0.947, 0.1357] reward=429.48 done=false error=null [STEP] step=31 action=[0.9533, 0.8989, 0.0589] reward=178.22 done=false error=null [STEP] step=32 action=[-0.946, -0.8272, 0.2743] reward=-42.66 done=false error=null [STEP] step=33 action=[0.944, 0.7355, 0.9401] reward=306.05 done=false error=null [STEP] step=34 action=[-0.973, 0.9273, -0.9841] reward=-8.95 done=false error=null [STEP] step=35 action=[-0.8319, 0.9233, -0.819] reward=-112.71 done=false error=null [STEP] step=36 action=[0.9398, 0.9505, -0.1156] reward=360.68 done=false error=null [STEP] step=37 action=[-0.9246, 0.9235, -0.9515] reward=41.47 done=false error=null [STEP] step=38 action=[-0.8897, 0.9412, -0.4163] reward=-20.86 done=false error=null [STEP] step=39 action=[-0.8721, 0.9343, 0.7109] reward=37.63 done=false error=null [STEP] step=40 action=[0.9732, 0.9631, 0.9089] reward=431.69 done=false error=null [STEP] step=41 action=[0.9545, 0.7974, -0.9612] reward=-73.76 done=false error=null [STEP] step=42 action=[-0.9051, -0.4575, -0.9736] reward=719.58 done=false error=null [STEP] step=43 action=[-0.9215, -0.8528, -0.9854] reward=914.28 done=false error=null [STEP] step=44 action=[-0.9813, -0.7875, -0.9874] reward=310.91 done=false error=null [STEP] step=45 action=[-0.8577, -0.4779, -0.9887] reward=0.00 done=false error=null [STEP] step=46 action=[-0.5824, 0.9649, 0.8061] reward=302.12 done=false error=null [STEP] step=47 action=[0.9625, 0.9559, 0.9776] reward=388.21 done=false error=null [STEP] step=48 action=[0.947, 0.2621, 0.9389] reward=299.28 done=false error=null [STEP] step=49 action=[0.9463, 0.9697, -0.3403] reward=0.00 done=false error=null [STEP] step=50 action=[0.1341, 0.9744, -0.2467] reward=0.00 done=false error=null [STEP] step=51 action=[0.6356, 0.9652, -0.861] reward=0.00 done=false error=null [STEP] step=52 action=[-0.9674, -0.7003, -0.4444] reward=85.23 done=false error=null [STEP] step=53 action=[0.9581, 0.8402, 0.6565] reward=367.80 done=false error=null [STEP] step=54 action=[0.9271, 0.8013, -0.3421] reward=47.74 done=false error=null [STEP] step=55 action=[-0.7443, 0.4649, 0.843] reward=0.00 done=false error=null [STEP] step=56 action=[-0.9825, -0.9199, -0.9657] reward=253.25 done=false error=null [STEP] step=57 action=[0.968, 0.9587, -0.7083] reward=361.89 done=false error=null [STEP] step=58 action=[0.8685, 0.84, -0.8736] reward=33.35 done=false error=null [STEP] step=59 action=[-0.9818, -0.1113, -0.9739] reward=8.82 done=false error=null [STEP] step=60 action=[-0.7178, 0.4796, 0.9175] reward=92.59 done=false error=null [STEP] step=61 action=[0.9728, 0.9228, 0.7115] reward=145.52 done=false error=null [STEP] step=62 action=[0.7475, 0.7192, -0.5016] reward=98.01 done=false error=null [STEP] step=63 action=[0.983, 0.4789, 0.8668] reward=0.00 done=false error=null [STEP] step=64 action=[0.9441, 0.926, 0.8235] reward=0.00 done=false error=null [STEP] step=65 action=[0.9666, 0.9501, -0.9667] reward=86.13 done=false error=null [STEP] step=66 action=[-0.9504, -0.8115, -0.9917] reward=803.09 done=false error=null [STEP] step=67 action=[0.9808, 0.9647, 0.9596] reward=-378.81 done=false error=null [STEP] step=68 action=[0.9531, 0.9717, -0.9842] reward=-22.61 done=false error=null [STEP] step=69 action=[-0.9812, -0.9671, -0.9984] reward=888.85 done=false error=null [STEP] step=70 action=[-0.9875, -0.9621, 0.6353] reward=-34.86 done=false error=null [STEP] step=71 action=[-0.8546, -0.8317, 0.1567] reward=144.64 done=false error=null [STEP] step=72 action=[-0.3122, -0.6563, -0.8786] reward=89.60 done=false error=null [STEP] step=73 action=[0.9413, 0.8492, 0.4922] reward=328.23 done=false error=null [STEP] step=74 action=[-0.9686, 0.8156, -0.924] reward=70.77 done=false error=null [STEP] step=75 action=[-0.9598, 0.2333, -0.6094] reward=91.63 done=false error=null [STEP] step=76 action=[0.8997, 0.7952, 0.8579] reward=322.23 done=false error=null [STEP] step=77 action=[-0.9702, 0.7416, -0.9579] reward=-54.20 done=false error=null [STEP] step=78 action=[0.9238, 0.8771, 0.9455] reward=322.03 done=false error=null [STEP] step=79 action=[0.6208, -0.1025, 0.8659] reward=145.99 done=false error=null [STEP] step=80 action=[-0.9421, -0.7, -0.4085] reward=99.08 done=false error=null [STEP] step=81 action=[-0.9223, -0.757, -0.5511] reward=-20.55 done=false error=null [STEP] step=82 action=[0.7985, 0.912, 0.7038] reward=306.71 done=false error=null [STEP] step=83 action=[0.8886, 0.9461, 0.9319] reward=257.30 done=false error=null [STEP] step=84 action=[0.9593, -0.5279, 0.9449] reward=152.97 done=false error=null [STEP] step=85 action=[-0.9179, -0.7843, 0.8214] reward=52.80 done=false error=null [STEP] step=86 action=[0.9165, -0.0702, 0.5106] reward=11.74 done=false error=null [STEP] step=87 action=[0.9791, 0.9752, 0.5583] reward=93.39 done=false error=null [STEP] step=88 action=[0.9779, 0.9747, 0.8894] reward=86.06 done=false error=null [STEP] step=89 action=[-0.9492, -0.8391, -0.9819] reward=779.72 done=false error=null [STEP] step=90 action=[0.7176, -0.1405, -0.9826] reward=321.24 done=false error=null [STEP] step=91 action=[0.8207, 0.9712, -0.9681] reward=-452.52 done=false error=null [STEP] step=92 action=[-0.9717, -0.7257, -0.9929] reward=620.25 done=false error=null [STEP] step=93 action=[-0.9702, -0.7903, -0.9936] reward=506.08 done=false error=null [STEP] step=94 action=[-0.9868, -0.9768, 0.915] reward=78.44 done=false error=null [STEP] step=95 action=[0.9892, 0.9881, 0.8133] reward=593.08 done=false error=null [STEP] step=96 action=[0.963, -0.745, 0.9588] reward=339.57 done=false error=null [STEP] step=97 action=[-0.9702, 0.8974, -0.6097] reward=46.74 done=false error=null [STEP] step=98 action=[-0.9574, -0.4879, -0.6432] reward=41.89 done=false error=null [STEP] step=99 action=[0.9499, 0.851, -0.8275] reward=467.16 done=false error=null [STEP] step=100 action=[0.2065, 0.8576, -0.8844] reward=25.37 done=false error=null [STEP] step=101 action=[0.7683, -0.0096, -0.2601] reward=173.42 done=false error=null [STEP] step=102 action=[-0.6898, 0.808, 0.2482] reward=61.35 done=false error=null [STEP] step=103 action=[0.6423, 0.7784, 0.8564] reward=200.09 done=false error=null [STEP] step=104 action=[-0.8082, -0.7556, 0.3757] reward=70.31 done=false error=null [STEP] step=105 action=[-0.9621, 0.7476, 0.5655] reward=135.49 done=false error=null [STEP] step=106 action=[-0.959, 0.9899, -0.854] reward=-127.23 done=false error=null [STEP] step=107 action=[0.9416, 0.9276, 0.7867] reward=563.31 done=false error=null [STEP] step=108 action=[0.3312, 0.8184, -0.5976] reward=90.41 done=false error=null [STEP] step=109 action=[-0.3417, 0.9286, -0.7496] reward=-16.52 done=false error=null [STEP] step=110 action=[0.8882, 0.9609, 0.2625] reward=256.14 done=false error=null [STEP] step=111 action=[0.9787, 0.9319, 0.917] reward=0.00 done=false error=null [STEP] step=112 action=[0.9759, 0.9823, 0.8041] reward=0.00 done=false error=null [STEP] step=113 action=[0.8857, -0.0462, -0.9585] reward=43.58 done=false error=null [STEP] step=114 action=[0.8438, -0.5688, -0.9152] reward=379.92 done=false error=null [STEP] step=115 action=[-0.8915, 0.6321, -0.9762] reward=597.75 done=false error=null [STEP] step=116 action=[-0.889, -0.9267, -0.991] reward=608.52 done=false error=null [STEP] step=117 action=[-0.991, -0.923, -0.994] reward=0.00 done=false error=null [STEP] step=118 action=[-0.7134, -0.9065, -0.6739] reward=0.00 done=false error=null [STEP] step=119 action=[-0.9625, -0.695, -0.867] reward=0.00 done=false error=null [STEP] step=120 action=[-0.9407, 0.8399, 0.1623] reward=5.56 done=false error=null [STEP] step=121 action=[0.919, 0.9675, 0.7483] reward=309.24 done=false error=null [STEP] step=122 action=[-0.9365, -0.7176, -0.9539] reward=139.64 done=false error=null [STEP] step=123 action=[0.671, -0.0364, -0.844] reward=0.00 done=false error=null [STEP] step=124 action=[0.9572, 0.9415, 0.6782] reward=419.64 done=false error=null [STEP] step=125 action=[-0.9435, -0.7017, -0.2677] reward=60.46 done=false error=null [STEP] step=126 action=[0.339, 0.527, 0.5517] reward=118.06 done=false error=null [STEP] step=127 action=[0.9661, 0.9374, -0.4119] reward=438.31 done=false error=null [STEP] step=128 action=[0.815, 0.7101, 0.5265] reward=214.04 done=false error=null [STEP] step=129 action=[0.9303, 0.0105, -0.8471] reward=0.00 done=false error=null [STEP] step=130 action=[-0.9251, 0.8455, -0.7301] reward=-51.12 done=false error=null [STEP] step=131 action=[-0.9839, -0.6239, -0.9698] reward=130.02 done=false error=null [STEP] step=132 action=[-0.9657, 0.9688, -0.6194] reward=9.89 done=false error=null [STEP] step=133 action=[0.8933, 0.9786, 0.8795] reward=249.48 done=false error=null [STEP] step=134 action=[0.9805, 0.9754, 0.9233] reward=299.10 done=false error=null [STEP] step=135 action=[0.9237, 0.9833, 0.9847] reward=358.92 done=false error=null [STEP] step=136 action=[0.9847, 0.9383, 0.8471] reward=86.24 done=false error=null [STEP] step=137 action=[-0.7683, -0.3056, -0.976] reward=649.03 done=false error=null [STEP] step=138 action=[-0.6282, -0.6385, -0.9527] reward=532.56 done=false error=null [STEP] step=139 action=[-0.6272, -0.2127, -0.9737] reward=204.69 done=false error=null [STEP] step=140 action=[-0.9849, -0.4828, -0.9891] reward=0.00 done=false error=null [STEP] step=141 action=[-0.9881, -0.9624, -0.827] reward=0.00 done=false error=null [STEP] step=142 action=[-0.8832, 0.6902, -0.438] reward=0.00 done=false error=null [STEP] step=143 action=[-0.9665, -0.7522, -0.4112] reward=0.00 done=false error=null [STEP] step=144 action=[-0.7552, -0.3327, -0.9294] reward=0.00 done=false error=null [STEP] step=145 action=[-0.6002, 0.7966, -0.8003] reward=0.00 done=false error=null [STEP] step=146 action=[0.6521, 0.9183, -0.7342] reward=151.41 done=false error=null [STEP] step=147 action=[-0.9631, 0.4908, -0.9684] reward=-51.47 done=false error=null [STEP] step=148 action=[0.5401, -0.2108, 0.7856] reward=236.04 done=false error=null [STEP] step=149 action=[-0.1426, 0.9183, 0.5719] reward=257.15 done=false error=null [STEP] step=150 action=[-0.942, -0.4963, 0.0684] reward=116.61 done=false error=null [STEP] step=151 action=[-0.9727, -0.9277, -0.9641] reward=160.39 done=false error=null [STEP] step=152 action=[0.9838, 0.9392, 0.1721] reward=395.79 done=false error=null [STEP] step=153 action=[-0.9583, 0.4341, 0.2439] reward=-30.91 done=false error=null [STEP] step=154 action=[-0.7129, -0.7055, -0.7434] reward=-24.25 done=false error=null [STEP] step=155 action=[-0.7837, -0.6132, 0.9052] reward=92.22 done=false error=null [STEP] step=156 action=[0.4096, -0.4453, 0.8794] reward=-5.85 done=false error=null [STEP] step=157 action=[0.6607, -0.734, -0.9436] reward=95.57 done=false error=null [STEP] step=158 action=[0.9694, 0.8355, 0.8585] reward=500.17 done=false error=null [STEP] step=159 action=[0.9851, 0.9713, 0.8468] reward=222.03 done=false error=null [STEP] step=160 action=[0.9602, 0.9418, 0.2576] reward=21.80 done=false error=null [STEP] step=161 action=[0.9312, 0.94, -0.9422] reward=98.12 done=false error=null [STEP] step=162 action=[-0.9005, -0.8968, -0.9903] reward=1064.42 done=false error=null [STEP] step=163 action=[0.9456, 0.9519, 0.8329] reward=-68.80 done=false error=null [STEP] step=164 action=[-0.9883, -0.4078, -0.9893] reward=730.73 done=false error=null [STEP] step=165 action=[-0.9456, 0.6673, -0.8769] reward=191.79 done=false error=null [STEP] step=166 action=[-0.9531, -0.9053, -0.8675] reward=-35.22 done=false error=null [STEP] step=167 action=[0.9535, -0.3165, 0.9673] reward=321.23 done=false error=null [STEP] step=168 action=[-0.7596, -0.7508, -0.9187] reward=-93.87 done=false error=null [END] success=false steps=168 score=0.286 rewards=0.00,82.05,-10.73,10.68,275.49,47.55,0.00,131.74,158.09,0.00,0.00,109.45,99.62,-76.22,0.00,0.00,629.52,1193.85,-342.85,479.34,75.39,334.05,348.65,-99.72,30.49,-57.14,407.38,337.09,-20.43,429.48,178.22,-42.66,306.05,-8.95,-112.71,360.68,41.47,-20.86,37.63,431.69,-73.76,719.58,914.28,310.91,0.00,302.12,388.21,299.28,0.00,0.00,0.00,85.23,367.80,47.74,0.00,253.25,361.89,33.35,8.82,92.59,145.52,98.01,0.00,0.00,86.13,803.09,-378.81,-22.61,888.85,-34.86,144.64,89.60,328.23,70.77,91.63,322.23,-54.20,322.03,145.99,99.08,-20.55,306.71,257.30,152.97,52.80,11.74,93.39,86.06,779.72,321.24,-452.52,620.25,506.08,78.44,593.08,339.57,46.74,41.89,467.16,25.37,173.42,61.35,200.09,70.31,135.49,-127.23,563.31,90.41,-16.52,256.14,0.00,0.00,43.58,379.92,597.75,608.52,0.00,0.00,0.00,5.56,309.24,139.64,0.00,419.64,60.46,118.06,438.31,214.04,0.00,-51.12,130.02,9.89,249.48,299.10,358.92,86.24,649.03,532.56,204.69,0.00,0.00,0.00,0.00,0.00,0.00,151.41,-51.47,236.04,257.15,116.61,160.39,395.79,-30.91,-24.25,92.22,-5.85,95.57,500.17,222.03,21.80,98.12,1064.42,-68.80,730.73,191.79,-35.22,321.23,-93.87 [DEBUG] Loaded weights for hard from safetensors bundle. [START] task=hard env=bess-rl model=meta-llama/Llama-3.1-8B-Instruct [STEP] step=1 action=[-0.8662, -0.9382, -0.9351] reward=0.00 done=false error=null [STEP] step=2 action=[-0.7279, -0.8504, -0.9592] reward=13.05 done=false error=null [STEP] step=3 action=[0.9905, -0.9307, 0.8936] reward=82.34 done=false error=null [STEP] step=4 action=[-0.9308, -0.9666, -0.9934] reward=129.76 done=false error=null [STEP] step=5 action=[0.9491, 0.5701, 0.3127] reward=197.10 done=false error=null [STEP] step=6 action=[-0.6176, -0.8677, -0.4255] reward=47.55 done=false error=null [STEP] step=7 action=[-0.7508, 0.3775, 0.9041] reward=96.86 done=false error=null [STEP] step=8 action=[0.8172, -0.2247, 0.594] reward=62.59 done=false error=null [STEP] step=9 action=[-0.3693, -0.9202, -0.7994] reward=175.17 done=false error=null [STEP] step=10 action=[-0.663, -0.9724, -0.5211] reward=45.97 done=false error=null [STEP] step=11 action=[-0.1238, -0.8774, 0.6042] reward=0.00 done=false error=null [STEP] step=12 action=[0.9726, -0.4656, -0.788] reward=-39.91 done=false error=null [STEP] step=13 action=[0.892, 0.9647, 0.9822] reward=10.93 done=false error=null [STEP] step=14 action=[-0.6079, 0.9666, 0.9203] reward=-248.57 done=false error=null [STEP] step=15 action=[0.7606, 0.9525, 0.5755] reward=113.96 done=false error=null [STEP] step=16 action=[0.6662, 0.983, 0.3858] reward=-37.05 done=false error=null [STEP] step=17 action=[-0.9177, -0.9347, -0.9613] reward=629.52 done=false error=null [STEP] step=18 action=[-0.9069, -0.9559, -0.7802] reward=1193.85 done=false error=null [STEP] step=19 action=[-0.1791, -0.7886, -0.3164] reward=147.35 done=false error=null [STEP] step=20 action=[-0.9243, 0.3336, -0.9813] reward=0.00 done=false error=null [STEP] step=21 action=[-0.9511, 0.0648, -0.9817] reward=0.00 done=false error=null [STEP] step=22 action=[0.7737, 0.9813, 0.9916] reward=238.23 done=false error=null [STEP] step=23 action=[0.6269, 0.9881, 0.9854] reward=259.31 done=false error=null [STEP] step=24 action=[-0.8136, 0.8548, 0.5067] reward=18.45 done=false error=null [STEP] step=25 action=[-0.9257, -0.9807, -0.9836] reward=92.86 done=false error=null [STEP] step=26 action=[0.9304, -0.9509, -0.3697] reward=-22.29 done=false error=null [STEP] step=27 action=[0.9843, -0.5205, 0.9387] reward=322.82 done=false error=null [STEP] step=28 action=[0.9728, 0.0458, 0.9359] reward=267.79 done=false error=null [STEP] step=29 action=[-0.8352, -0.2796, -0.8389] reward=-20.43 done=false error=null [STEP] step=30 action=[0.9748, 0.9712, 0.4923] reward=354.21 done=false error=null [STEP] step=31 action=[0.9339, 0.9742, 0.6408] reward=130.50 done=false error=null [STEP] step=32 action=[-0.0961, 0.3876, -0.5317] reward=65.26 done=false error=null [STEP] step=33 action=[0.8653, 0.9427, 0.6576] reward=77.69 done=false error=null [STEP] step=34 action=[0.5896, -0.9803, -0.3124] reward=-6.29 done=false error=null [STEP] step=35 action=[0.9565, -0.2441, 0.418] reward=49.74 done=false error=null [STEP] step=36 action=[0.9508, 0.9826, 0.7286] reward=0.00 done=false error=null [STEP] step=37 action=[-0.586, 0.6789, 0.9675] reward=0.00 done=false error=null [STEP] step=38 action=[0.659, 0.1426, 0.7084] reward=-19.74 done=false error=null [STEP] step=39 action=[0.3061, 0.6416, 0.6501] reward=-26.40 done=false error=null [STEP] step=40 action=[0.8981, 0.9591, 0.8406] reward=-7.07 done=false error=null [STEP] step=41 action=[0.9206, -0.8081, 0.9811] reward=-6.44 done=false error=null [STEP] step=42 action=[-0.9214, -0.9077, -0.9682] reward=719.58 done=false error=null [STEP] step=43 action=[-0.9573, -0.9595, -0.9299] reward=914.28 done=false error=null [STEP] step=44 action=[-0.9781, -0.8369, -0.9692] reward=310.91 done=false error=null [STEP] step=45 action=[-0.9516, -0.8483, -0.9588] reward=0.00 done=false error=null [STEP] step=46 action=[0.6996, 0.7858, 0.305] reward=209.96 done=false error=null [STEP] step=47 action=[0.8214, 0.9758, 0.9511] reward=291.89 done=false error=null [STEP] step=48 action=[0.963, 0.9758, 0.9664] reward=262.88 done=false error=null [STEP] step=49 action=[0.9848, 0.9751, 0.2698] reward=0.00 done=false error=null [STEP] step=50 action=[0.9649, -0.6302, 0.8294] reward=0.00 done=false error=null [STEP] step=51 action=[0.9905, -0.8552, 0.9696] reward=0.00 done=false error=null [STEP] step=52 action=[-0.8028, -0.9651, -0.9799] reward=85.23 done=false error=null [STEP] step=53 action=[0.9751, 0.938, 0.8829] reward=302.71 done=false error=null [STEP] step=54 action=[0.9785, 0.9499, -0.4642] reward=47.74 done=false error=null [STEP] step=55 action=[0.7469, -0.416, -0.3557] reward=-3.19 done=false error=null [STEP] step=56 action=[-0.9469, -0.942, -0.9798] reward=253.25 done=false error=null [STEP] step=57 action=[0.9683, 0.963, 0.9297] reward=280.65 done=false error=null [STEP] step=58 action=[0.967, 0.9645, -0.0487] reward=18.52 done=false error=null [STEP] step=59 action=[0.5099, -0.5663, 0.7484] reward=0.00 done=false error=null [STEP] step=60 action=[0.767, 0.1946, 0.3847] reward=84.55 done=false error=null [STEP] step=61 action=[0.8451, 0.9015, 0.7849] reward=78.34 done=false error=null [STEP] step=62 action=[0.8617, -0.3755, 0.6282] reward=79.16 done=false error=null [STEP] step=63 action=[-0.5477, 0.964, 0.9733] reward=-19.64 done=false error=null [STEP] step=64 action=[0.5346, 0.9659, 0.6935] reward=-16.44 done=false error=null [STEP] step=65 action=[0.9548, -0.5813, -0.9274] reward=270.71 done=false error=null [STEP] step=66 action=[-0.9667, -0.869, -0.9593] reward=803.09 done=false error=null [STEP] step=67 action=[-0.5006, 0.9208, 0.961] reward=-517.73 done=false error=null [STEP] step=68 action=[0.9711, -0.9769, -0.819] reward=172.61 done=false error=null [STEP] step=69 action=[-0.9681, -0.6843, -0.9577] reward=798.82 done=false error=null [STEP] step=70 action=[-0.5104, 0.8948, -0.6597] reward=81.86 done=false error=null [STEP] step=71 action=[0.9869, -0.8458, -0.9884] reward=0.00 done=false error=null [STEP] step=72 action=[-0.8404, 0.9726, 0.8846] reward=177.66 done=false error=null [STEP] step=73 action=[0.8733, -0.925, 0.9648] reward=219.83 done=false error=null [STEP] step=74 action=[-0.5991, -0.4749, -0.8953] reward=78.41 done=false error=null [STEP] step=75 action=[-0.9294, -0.9483, -0.9772] reward=79.40 done=false error=null [STEP] step=76 action=[0.9605, 0.397, 0.9488] reward=237.32 done=false error=null [STEP] step=77 action=[-0.4095, -0.9013, -0.8666] reward=-54.20 done=false error=null [STEP] step=78 action=[0.9272, 0.9343, 0.8675] reward=249.55 done=false error=null [STEP] step=79 action=[-0.8857, 0.9772, 0.889] reward=50.70 done=false error=null [STEP] step=80 action=[0.4167, -0.9562, -0.8342] reward=99.08 done=false error=null [STEP] step=81 action=[0.3333, 0.8822, 0.2481] reward=-53.94 done=false error=null [STEP] step=82 action=[0.8754, 0.9505, -0.3643] reward=132.98 done=false error=null [STEP] step=83 action=[0.9581, 0.9927, 0.8812] reward=64.61 done=false error=null [STEP] step=84 action=[0.9062, 0.9667, 0.6836] reward=0.00 done=false error=null [STEP] step=85 action=[0.395, -0.7913, 0.4823] reward=49.38 done=false error=null [STEP] step=86 action=[0.8772, -0.6472, 0.5119] reward=79.22 done=false error=null [STEP] step=87 action=[0.9424, 0.9772, 0.9442] reward=74.08 done=false error=null [STEP] step=88 action=[0.9249, 0.9776, 0.9582] reward=49.31 done=false error=null [STEP] step=89 action=[-0.9178, -0.9569, -0.9665] reward=779.72 done=false error=null [STEP] step=90 action=[0.6328, -0.7218, -0.8859] reward=564.35 done=false error=null [STEP] step=91 action=[0.3262, -0.3863, -0.3824] reward=309.05 done=false error=null [STEP] step=92 action=[-0.9358, -0.2767, -0.9729] reward=77.07 done=false error=null [STEP] step=93 action=[-0.9288, -0.4313, -0.9838] reward=0.00 done=false error=null [STEP] step=94 action=[-0.8668, 0.9605, -0.876] reward=78.44 done=false error=null [STEP] step=95 action=[-0.2571, 0.9867, 0.9931] reward=538.20 done=false error=null [STEP] step=96 action=[-0.4886, 0.9934, 0.9513] reward=262.76 done=false error=null [STEP] step=97 action=[-0.9364, -0.9423, -0.9633] reward=68.48 done=false error=null [STEP] step=98 action=[-0.77, -0.9849, -0.9619] reward=33.72 done=false error=null [STEP] step=99 action=[0.9773, 0.9284, 0.3196] reward=414.51 done=false error=null [STEP] step=100 action=[0.9543, -0.7397, 0.9133] reward=75.99 done=false error=null [STEP] step=101 action=[0.9518, -0.8253, 0.9738] reward=195.96 done=false error=null [STEP] step=102 action=[0.9378, -0.2481, 0.9859] reward=0.00 done=false error=null [STEP] step=103 action=[0.9646, 0.631, 0.9322] reward=0.00 done=false error=null [STEP] step=104 action=[-0.6942, -0.8164, -0.2761] reward=70.31 done=false error=null [STEP] step=105 action=[0.3489, 0.5014, 0.926] reward=53.03 done=false error=null [STEP] step=106 action=[0.9658, -0.4485, -0.7371] reward=-33.97 done=false error=null [STEP] step=107 action=[0.7091, 0.8055, 0.3126] reward=240.05 done=false error=null [STEP] step=108 action=[0.7916, 0.9314, 0.611] reward=76.98 done=false error=null [STEP] step=109 action=[0.9073, -0.0021, 0.1958] reward=76.12 done=false error=null [STEP] step=110 action=[0.0903, 0.9527, 0.4613] reward=-0.95 done=false error=null [STEP] step=111 action=[0.7732, 0.9842, 0.6788] reward=0.00 done=false error=null [STEP] step=112 action=[0.972, 0.925, -0.0089] reward=-32.17 done=false error=null [STEP] step=113 action=[0.8775, 0.9694, 0.6996] reward=-23.19 done=false error=null [STEP] step=114 action=[-0.1542, -0.1662, -0.9092] reward=593.45 done=false error=null [STEP] step=115 action=[-0.9107, -0.3506, -0.9719] reward=597.75 done=false error=null [STEP] step=116 action=[-0.959, -0.9567, -0.5818] reward=370.59 done=false error=null [STEP] step=117 action=[-0.9494, -0.9063, -0.9936] reward=0.00 done=false error=null [STEP] step=118 action=[0.2542, -0.8184, -0.7066] reward=0.00 done=false error=null [STEP] step=119 action=[-0.9827, 0.0679, -0.9301] reward=0.00 done=false error=null [STEP] step=120 action=[-0.1717, 0.8976, -0.7155] reward=0.94 done=false error=null [STEP] step=121 action=[0.9835, -0.7079, 0.9593] reward=226.14 done=false error=null [STEP] step=122 action=[-0.9375, -0.9626, -0.9922] reward=132.92 done=false error=null [STEP] step=123 action=[0.9132, -0.9926, 0.7446] reward=160.47 done=false error=null [STEP] step=124 action=[0.9714, 0.2134, 0.973] reward=352.93 done=false error=null [STEP] step=125 action=[-0.7904, -0.868, -0.9258] reward=66.99 done=false error=null [STEP] step=126 action=[0.4562, 0.1859, 0.0342] reward=38.71 done=false error=null [STEP] step=127 action=[0.9448, 0.9087, 0.7971] reward=347.53 done=false error=null [STEP] step=128 action=[0.9413, 0.3001, 0.2638] reward=161.65 done=false error=null [STEP] step=129 action=[0.9405, 0.9482, 0.5733] reward=0.00 done=false error=null [STEP] step=130 action=[0.4443, -0.0814, 0.29] reward=-16.63 done=false error=null [STEP] step=131 action=[-0.7068, -0.9554, 0.4601] reward=130.02 done=false error=null [STEP] step=132 action=[0.0326, -0.5671, 0.5784] reward=-37.40 done=false error=null [STEP] step=133 action=[0.9727, 0.9428, 0.782] reward=113.41 done=false error=null [STEP] step=134 action=[0.9721, 0.9761, 0.9604] reward=-5.19 done=false error=null [STEP] step=135 action=[0.9589, 0.9808, -0.3264] reward=-29.39 done=false error=null [STEP] step=136 action=[0.8469, 0.9807, 0.9548] reward=86.24 done=false error=null [STEP] step=137 action=[-0.8775, -0.9168, -0.9782] reward=649.03 done=false error=null [STEP] step=138 action=[0.1807, 0.0889, -0.8347] reward=300.95 done=false error=null [STEP] step=139 action=[0.4447, 0.0551, -0.6679] reward=91.76 done=false error=null [STEP] step=140 action=[-0.9428, 0.1667, -0.9841] reward=363.75 done=false error=null [STEP] step=141 action=[-0.9662, 0.1541, -0.9825] reward=0.00 done=false error=null [STEP] step=142 action=[-0.4248, 0.4004, 0.052] reward=-4.39 done=false error=null [STEP] step=143 action=[-0.906, 0.64, -0.6445] reward=2.02 done=false error=null [STEP] step=144 action=[-0.73, 0.9008, 0.7976] reward=125.37 done=false error=null [STEP] step=145 action=[0.9212, -0.2631, 0.7444] reward=69.32 done=false error=null [STEP] step=146 action=[0.9687, -0.6188, 0.4701] reward=78.72 done=false error=null [STEP] step=147 action=[-0.7654, -0.1967, -0.8636] reward=-68.20 done=false error=null [STEP] step=148 action=[0.9516, -0.7854, 0.8734] reward=158.19 done=false error=null [STEP] step=149 action=[0.9519, 0.5417, 0.9677] reward=123.92 done=false error=null [STEP] step=150 action=[-0.1039, -0.9553, -0.9551] reward=116.61 done=false error=null [STEP] step=151 action=[-0.8956, -0.9448, -0.9742] reward=199.24 done=false error=null [STEP] step=152 action=[0.9673, 0.9466, 0.865] reward=322.82 done=false error=null [STEP] step=153 action=[-0.4737, 0.8767, 0.9117] reward=44.82 done=false error=null [STEP] step=154 action=[0.7658, -0.9159, -0.5305] reward=-26.53 done=false error=null [STEP] step=155 action=[0.9297, -0.3484, -0.5565] reward=59.38 done=false error=null [STEP] step=156 action=[0.8481, -0.9322, 0.2444] reward=49.71 done=false error=null [STEP] step=157 action=[-0.8945, -0.8456, 0.6803] reward=125.52 done=false error=null [STEP] step=158 action=[0.689, 0.97, 0.9916] reward=395.50 done=false error=null [STEP] step=159 action=[0.4792, 0.9906, 0.9661] reward=90.24 done=false error=null [STEP] step=160 action=[-0.1491, 0.8481, 0.9766] reward=87.56 done=false error=null [STEP] step=161 action=[0.9675, -0.3325, -0.8485] reward=180.04 done=false error=null [STEP] step=162 action=[-0.9181, -0.9961, -0.9835] reward=1064.42 done=false error=null [STEP] step=163 action=[0.8827, 0.9861, 0.9973] reward=-186.47 done=false error=null [STEP] step=164 action=[-0.9622, -0.3597, -0.9794] reward=730.73 done=false error=null [STEP] step=165 action=[0.0099, -0.9469, -0.9197] reward=191.79 done=false error=null [STEP] step=166 action=[-0.8699, 0.9253, 0.7355] reward=44.02 done=false error=null [STEP] step=167 action=[-0.4712, 0.9864, 0.9723] reward=232.06 done=false error=null [STEP] step=168 action=[-0.79, 0.7032, -0.8292] reward=-95.28 done=false error=null [END] success=false steps=168 score=0.260 rewards=0.00,13.05,82.34,129.76,197.10,47.55,96.86,62.59,175.17,45.97,0.00,-39.91,10.93,-248.57,113.96,-37.05,629.52,1193.85,147.35,0.00,0.00,238.23,259.31,18.45,92.86,-22.29,322.82,267.79,-20.43,354.21,130.50,65.26,77.69,-6.29,49.74,0.00,0.00,-19.74,-26.40,-7.07,-6.44,719.58,914.28,310.91,0.00,209.96,291.89,262.88,0.00,0.00,0.00,85.23,302.71,47.74,-3.19,253.25,280.65,18.52,0.00,84.55,78.34,79.16,-19.64,-16.44,270.71,803.09,-517.73,172.61,798.82,81.86,0.00,177.66,219.83,78.41,79.40,237.32,-54.20,249.55,50.70,99.08,-53.94,132.98,64.61,0.00,49.38,79.22,74.08,49.31,779.72,564.35,309.05,77.07,0.00,78.44,538.20,262.76,68.48,33.72,414.51,75.99,195.96,0.00,0.00,70.31,53.03,-33.97,240.05,76.98,76.12,-0.95,0.00,-32.17,-23.19,593.45,597.75,370.59,0.00,0.00,0.00,0.94,226.14,132.92,160.47,352.93,66.99,38.71,347.53,161.65,0.00,-16.63,130.02,-37.40,113.41,-5.19,-29.39,86.24,649.03,300.95,91.76,363.75,0.00,-4.39,2.02,125.37,69.32,78.72,-68.20,158.19,123.92,116.61,199.24,322.82,44.82,-26.53,59.38,49.71,125.52,395.50,90.24,87.56,180.04,1064.42,-186.47,730.73,191.79,44.02,232.06,-95.28